Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gertsylvest/meta-team --skill faust-buildgit clone --depth 1 https://github.com/gertsylvest/meta-teamWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gertsylvest/meta-team/faust-build)<a href="https://agentmods.dev/skills/gertsylvest/meta-team/faust-build"><img src="https://agentmods.dev/badge/skills/gertsylvest/meta-team/faust-build/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gertsylvest/meta-team/faust-build"><img src="https://agentmods.dev/badge/skills/gertsylvest/meta-team/faust-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.01290 |
| Opus 5 | $0.00028 | $0.00645 |
| Sonnet 5 | $0.00011 | $0.00258 |
| Haiku 4.5 | $0.00006 | $0.00129 |
Grade A, and why
faust-build scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Faust Build
Compile a Faust DSP source file to C and verify the result is structurally correct. Combines three steps that were performed manually on every DSP change: parameter audit, compilation, and API surface verification. Optionally adds a clang compile step to catch type errors early.
Requirements
- Faust compiler on
PATH(or specify binary with--faust). Tested against Faust 2.85.x.- Known issue:
-ftz 2generates broken C in Faust 2.85.5. This script defaults to-ftz 0(see--ftzoption).
- Known issue:
- clang (optional, only needed for
--clangstep) - Faust architecture headers (optional, only needed for
--clang): the directory containingfaust/gui/CInterface.h. Pass via--faust-arch.
Instructions
Arguments are in $ARGUMENTS. Pass them directly to the build script:
bash "$(dirname "$0")/build.sh" $ARGUMENTS
Steps performed
| Step | What it does |
|---|---|
| 0 — Param audit | Scans the .dsp source for hslider/vslider/nentry parameters not followed by si.smoo or si.smooth on the same line. Flags as warnings (heuristic; does not catch multi-line smoothing). |
| 1 — Faust compile | Runs faust -lang c -cn <ClassName> -single -ftz <N> <include paths> -o <output.c> <input.dsp>. Aborts on compiler failure. |
| 2 — API surface check | Greps the generated C for all 14 expected public function names (suffix = class name). Checks that FAUSTCLASS macro matches. Optionally verifies getNumInputs and getNumOutputs return values. |
| 3 — Clang compile (optional) | Runs clang -std=c11 -O2 -Wall -Wextra -include faust/gui/CInterface.h -Wno-unused-parameter -c <output.c>. The force-include is required because Faust-generated C references UIGlue, MetaGlue, and Soundfile without including their definitions. |
Options
| Option | Default | Description |
|---|---|---|
--cn NAME |
mydsp |
Faust class name (-cn flag). All generated function names are suffixed with this. |
-I PATH |
— | Include path for Faust library resolution (repeatable). Typically needs dsp/modules and the faustlibraries path. |
--faust BIN |
faust |
Faust compiler binary path. |
--faust-arch DIR |
— | Directory containing faust/gui/CInterface.h. Required for --clang. |
--ftz N |
0 |
Faust denormal flushing mode. Use 0 for Faust 2.85.x (the default); -ftz 2 is broken in that version. |
--clang |
off | Run clang -c -Wall on the generated C as a final verification step. |
--inputs N |
— | Expected getNumInputs return value. Fails if the generated code disagrees. |
--outputs N |
— | Expected getNumOutputs return value. Fails if the generated code disagrees. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 82 lines · 55 tokens per session scan A 7ed7cc818dc9
faust-build is a skill published in the GitHub repository gertsylvest/meta-team (5 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,290 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…